Transform Weather Sensor Data from Waggle to an Xarray Dataset + Plot with ACT

Imports

import sage_data_client
from bokeh.models.formatters import DatetimeTickFormatter
import hvplot.pandas
import hvplot.xarray
import holoviews as hv
import cartopy.crs as ccrs
import cartopy.feature as cfeature
import xarray as xr
import matplotlib.pyplot as plt
from metpy.plots import USCOUNTIES
import act
import numpy as np
import pandas as pd
import warnings
from bokeh.models import DatetimeTickFormatter

def apply_formatter(plot, element):
    plot.handles['xaxis'].formatter = DatetimeTickFormatter(hours='%m/%d/%Y \n %H:%M',
                                                            minutes='%m/%d/%Y \n %H:%M',
                                                            hourmin='%m/%d/%Y \n %H:%M',
                                                            days='%m/%d/%Y \n %H:%M',
                                                            months='%m/%d/%Y \n %H:%M')
xr.set_options(keep_attrs=True)
warnings.filterwarnings("ignore")
hv.extension("bokeh")

Query for the available Data

wxt_df = sage_data_client.query(
    start="-3h",
    filter={
        "sensor": "vaisala-wxt536"
    }
)

---------------------------------------------------------------------------
TimeoutError                              Traceback (most recent call last)
File ~/miniconda3/envs/instrument-cookbooks-dev/lib/python3.10/urllib/request.py:1348, in AbstractHTTPHandler.do_open(self, http_class, req, **http_conn_args)
   1347 try:
-> 1348     h.request(req.get_method(), req.selector, req.data, headers,
   1349               encode_chunked=req.has_header('Transfer-encoding'))
   1350 except OSError as err: # timeout error

File ~/miniconda3/envs/instrument-cookbooks-dev/lib/python3.10/http/client.py:1283, in HTTPConnection.request(self, method, url, body, headers, encode_chunked)
   1282 """Send a complete request to the server."""
-> 1283 self._send_request(method, url, body, headers, encode_chunked)

File ~/miniconda3/envs/instrument-cookbooks-dev/lib/python3.10/http/client.py:1329, in HTTPConnection._send_request(self, method, url, body, headers, encode_chunked)
   1328     body = _encode(body, 'body')
-> 1329 self.endheaders(body, encode_chunked=encode_chunked)

File ~/miniconda3/envs/instrument-cookbooks-dev/lib/python3.10/http/client.py:1278, in HTTPConnection.endheaders(self, message_body, encode_chunked)
   1277     raise CannotSendHeader()
-> 1278 self._send_output(message_body, encode_chunked=encode_chunked)

File ~/miniconda3/envs/instrument-cookbooks-dev/lib/python3.10/http/client.py:1038, in HTTPConnection._send_output(self, message_body, encode_chunked)
   1037 del self._buffer[:]
-> 1038 self.send(msg)
   1040 if message_body is not None:
   1041 
   1042     # create a consistent interface to message_body

File ~/miniconda3/envs/instrument-cookbooks-dev/lib/python3.10/http/client.py:976, in HTTPConnection.send(self, data)
    975 if self.auto_open:
--> 976     self.connect()
    977 else:

File ~/miniconda3/envs/instrument-cookbooks-dev/lib/python3.10/http/client.py:1448, in HTTPSConnection.connect(self)
   1446 "Connect to a host on a given (SSL) port."
-> 1448 super().connect()
   1450 if self._tunnel_host:

File ~/miniconda3/envs/instrument-cookbooks-dev/lib/python3.10/http/client.py:942, in HTTPConnection.connect(self)
    941 sys.audit("http.client.connect", self, self.host, self.port)
--> 942 self.sock = self._create_connection(
    943     (self.host,self.port), self.timeout, self.source_address)
    944 # Might fail in OSs that don't implement TCP_NODELAY

File ~/miniconda3/envs/instrument-cookbooks-dev/lib/python3.10/socket.py:857, in create_connection(address, timeout, source_address)
    856 try:
--> 857     raise err
    858 finally:
    859     # Break explicitly a reference cycle

File ~/miniconda3/envs/instrument-cookbooks-dev/lib/python3.10/socket.py:845, in create_connection(address, timeout, source_address)
    844     sock.bind(source_address)
--> 845 sock.connect(sa)
    846 # Break explicitly a reference cycle

TimeoutError: [Errno 110] Connection timed out

During handling of the above exception, another exception occurred:

URLError                                  Traceback (most recent call last)
Cell In[2], line 1
----> 1 wxt_df = sage_data_client.query(
      2     start="-3h",
      3     filter={
      4         "sensor": "vaisala-wxt536"
      5     }
      6 )

File ~/miniconda3/envs/instrument-cookbooks-dev/lib/python3.10/site-packages/sage_data_client/query.py:115, in query(start, end, head, tail, filter, endpoint, bucket, experimental_func, experimental_window)
    112 headers = {"Accept-Encoding": "gzip"}
    113 req = Request(endpoint, data, headers=headers)
--> 115 with urlopen(req) as f:
    116     content_encoding = f.headers.get("Content-Encoding", "")
    117     if "gzip" in content_encoding:

File ~/miniconda3/envs/instrument-cookbooks-dev/lib/python3.10/urllib/request.py:216, in urlopen(url, data, timeout, cafile, capath, cadefault, context)
    214 else:
    215     opener = _opener
--> 216 return opener.open(url, data, timeout)

File ~/miniconda3/envs/instrument-cookbooks-dev/lib/python3.10/urllib/request.py:519, in OpenerDirector.open(self, fullurl, data, timeout)
    516     req = meth(req)
    518 sys.audit('urllib.Request', req.full_url, req.data, req.headers, req.get_method())
--> 519 response = self._open(req, data)
    521 # post-process response
    522 meth_name = protocol+"_response"

File ~/miniconda3/envs/instrument-cookbooks-dev/lib/python3.10/urllib/request.py:536, in OpenerDirector._open(self, req, data)
    533     return result
    535 protocol = req.type
--> 536 result = self._call_chain(self.handle_open, protocol, protocol +
    537                           '_open', req)
    538 if result:
    539     return result

File ~/miniconda3/envs/instrument-cookbooks-dev/lib/python3.10/urllib/request.py:496, in OpenerDirector._call_chain(self, chain, kind, meth_name, *args)
    494 for handler in handlers:
    495     func = getattr(handler, meth_name)
--> 496     result = func(*args)
    497     if result is not None:
    498         return result

File ~/miniconda3/envs/instrument-cookbooks-dev/lib/python3.10/urllib/request.py:1391, in HTTPSHandler.https_open(self, req)
   1390 def https_open(self, req):
-> 1391     return self.do_open(http.client.HTTPSConnection, req,
   1392         context=self._context, check_hostname=self._check_hostname)

File ~/miniconda3/envs/instrument-cookbooks-dev/lib/python3.10/urllib/request.py:1351, in AbstractHTTPHandler.do_open(self, http_class, req, **http_conn_args)
   1348         h.request(req.get_method(), req.selector, req.data, headers,
   1349                   encode_chunked=req.has_header('Transfer-encoding'))
   1350     except OSError as err: # timeout error
-> 1351         raise URLError(err)
   1352     r = h.getresponse()
   1353 except:

URLError: <urlopen error [Errno 110] Connection timed out>

Configure Helper Functions and Renaming Conventions

The renaming is required due to . notations being problematic when working with both Pandas and Xarray data structures.

variable_rename_dict = {'wxt.env.humidity':'air_humidity',
                        'wxt.env.pressure':'air_pressure',
                        'wxt.env.temp':'air_temperature',
                        'wxt.heater.temp':'heater_temperature',
                        'wxt.heater.volt':'heater_voltage',
                        'wxt.rain.accumulation':'rain_accumulation',
                        'wxt.wind.direction':'wind_direction',
                        'wxt.wind.speed':'wind_speed',
                        'sys.gps.lat':'latitude',
                        'sys.gps.lon':'longitude',
                    }

def generate_data_array(df, variable, rename_variable_dict=variable_rename_dict):
    new_variable_name = rename_variable_dict[variable]
    df_variable= df.loc[df.name == variable]
    ds = df_variable.to_xarray().rename({'value':new_variable_name,
                                         'timestamp':'time',
                                         'meta.vsn':'node'})
    ds[new_variable_name].attrs['units'] = df_variable['meta.units'].values[0]
    ds['time'] = pd.to_datetime(ds.time)
    ds.attrs['datastream'] = ds.node.values[0]
    return ds[[new_variable_name]]

def generate_dataset(df, variables, rename_variable_dict=variable_rename_dict):
    reindexed = df.set_index(['meta.vsn', 'timestamp'])
    return xr.merge([generate_data_array(reindexed, variable) for variable in variables])

Transform the Data to Xarray

wxt_variables = wxt_df.name.unique()
wxt_variables

array(['wxt.env.humidity', 'wxt.env.pressure', 'wxt.env.temp',
       'wxt.heater.temp', 'wxt.heater.volt', 'wxt.rain.accumulation',
       'wxt.wind.direction', 'wxt.wind.speed'], dtype=object)

wxt_ds = generate_dataset(wxt_df, wxt_variables).squeeze()
wxt_ds

<xarray.Dataset>
Dimensions:             (time: 134566)
Coordinates:
    node                <U4 'W057'
  * time                (time) datetime64[ns] 2023-04-14T17:59:43.475266934 ....
Data variables:
    air_humidity        (time) float64 35.2 35.2 35.2 35.2 ... nan nan nan nan
    air_pressure        (time) float64 981.4 981.4 981.4 ... 980.1 980.1 980.1
    air_temperature     (time) float64 24.9 24.9 24.9 24.9 ... 26.3 26.3 26.3
    heater_temperature  (time) float64 30.9 30.9 30.9 30.9 ... 30.8 30.8 30.8
    heater_voltage      (time) float64 0.0 0.0 0.0 0.0 0.0 ... 0.0 0.0 0.0 0.0
    rain_accumulation   (time) float64 0.03 0.03 0.03 0.03 ... 0.03 0.03 0.03
    wind_direction      (time) float64 181.0 181.0 185.0 ... 163.0 163.0 163.0
    wind_speed          (time) float64 2.9 2.9 2.8 2.8 2.8 ... 2.7 2.8 2.8 2.8
Attributes:
    datastream:  W057

xarray.Dataset

• Dimensions:
  • time: 134566
• Coordinates: (2)
  • node
    ()
    <U4
    'W057'

    array('W057', dtype='<U4')

  • time
    (time)
    datetime64[ns]
    2023-04-14T17:59:43.475266934 .....

    array(['2023-04-14T17:59:43.475266934', '2023-04-14T17:59:43.549903215',
           '2023-04-14T17:59:43.718253933', ..., '2023-04-14T20:59:43.596753288',
           '2023-04-14T20:59:43.672562546', '2023-04-14T20:59:43.748872004'],
          dtype='datetime64[ns]')

• Data variables: (8)
  • air_humidity
    (time)
    float64
    35.2 35.2 35.2 35.2 ... nan nan nan

    units :

    percent

    array([35.2, 35.2, 35.2, ...,  nan,  nan,  nan])

  • air_pressure
    (time)
    float64
    981.4 981.4 981.4 ... 980.1 980.1

    units :

    hectoPascal

    array([981.4, 981.4, 981.4, ..., 980.1, 980.1, 980.1])

  • air_temperature
    (time)
    float64
    24.9 24.9 24.9 ... 26.3 26.3 26.3

    units :

    degree Celsius

    array([24.9, 24.9, 24.9, ..., 26.3, 26.3, 26.3])

  • heater_temperature
    (time)
    float64
    30.9 30.9 30.9 ... 30.8 30.8 30.8

    units :

    degree Celsius

    array([30.9, 30.9, 30.9, ..., 30.8, 30.8, 30.8])

  • heater_voltage
    (time)
    float64
    0.0 0.0 0.0 0.0 ... 0.0 0.0 0.0 0.0

    units :

    volts

    array([0., 0., 0., ..., 0., 0., 0.])

  • rain_accumulation
    (time)
    float64
    0.03 0.03 0.03 ... 0.03 0.03 0.03

    units :

    milimeters

    array([0.03, 0.03, 0.03, ..., 0.03, 0.03, 0.03])

  • wind_direction
    (time)
    float64
    181.0 181.0 185.0 ... 163.0 163.0

    units :

    degrees

    array([181., 181., 185., ..., 163., 163., 163.])

  • wind_speed
    (time)
    float64
    2.9 2.9 2.8 2.8 ... 2.7 2.8 2.8 2.8

    units :

    meters per second

    array([2.9, 2.9, 2.8, ..., 2.8, 2.8, 2.8])

• Indexes: (1)
  • time
    PandasIndex

    PandasIndex(DatetimeIndex(['2023-04-14 17:59:43.475266934',
                   '2023-04-14 17:59:43.549903215',
                   '2023-04-14 17:59:43.718253933',
                   '2023-04-14 17:59:43.793684050',
                   '2023-04-14 17:59:43.869524062',
                   '2023-04-14 17:59:43.951531819',
                   '2023-04-14 17:59:44.026595627',
                   '2023-04-14 17:59:44.102201587',
                   '2023-04-14 17:59:44.177617720',
                   '2023-04-14 17:59:44.252600150',
                   ...
                   '2023-04-14 20:59:43.065794079',
                   '2023-04-14 20:59:43.140582550',
                   '2023-04-14 20:59:43.217408754',
                   '2023-04-14 20:59:43.292724659',
                   '2023-04-14 20:59:43.367861968',
                   '2023-04-14 20:59:43.442852907',
                   '2023-04-14 20:59:43.518273645',
                   '2023-04-14 20:59:43.596753288',
                   '2023-04-14 20:59:43.672562546',
                   '2023-04-14 20:59:43.748872004'],
                  dtype='datetime64[ns]', name='time', length=134566, freq=None))

• Attributes: (1)

  datastream :

  W057

Resample the data to minute requency

minute_ds = wxt_ds.resample(time='1T').mean()

Visualize using hvplot

meteogram_variables = ['air_temperature', 'air_humidity', 'wind_speed', 'wind_direction']
plots = []
for variable in meteogram_variables:
    plots.append(wxt_ds[variable].hvplot.line(label='10 Hz Data') * 
                 minute_ds[variable].hvplot.line(label='1 Minute Data'))
hv.Layout(plots).cols(2)

Plot Using the Atmospheric Data Community Toolkit (ACT)

WindDisplay = act.plotting.WindRoseDisplay(minute_ds, figsize=(8, 10), subplot_shape=(1,))
WindDisplay.plot(
    'wind_direction', 'wind_speed', spd_bins=np.linspace(0, 25, 5), num_dirs=30, tick_interval=2, subplot_index=(0,)
)

<PolarAxes: title={'center': 'W057 on 20230414'}>